© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116141
    Prev
    Next
    INDEX
    Explanations

    that followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بذلك
    -0.07
     didn
    -0.07
     моей
    -0.06
     believed
    -0.06
     my
    -0.06
     meiner
    -0.06
     seemed
    -0.06
     شاید
    -0.06
     reported
    -0.06
     ESO
    -0.06
    POSITIVE LOGITS
     from
    0.08
     từ
    0.07
    ದಿಂದ
    0.07
    ಿಯಿಂದ
    0.07
    부터
    0.07
    from
    0.06
     impose
    0.06
    から
    0.06
     as
    0.06
     for
    0.06
    Activations Density 0.006%

    No Known Activations